本研究發展了一個動態手勢辨識系統，整個系統由四個部份組成：收集手勢資料、擷取特徵值、建構隱藏馬可夫模型、辨識手勢。首先使用者在手部的關節及指尖必須貼上反光球，我們利用八部Vicon Motion Systems的攝影機拍攝手部的動作，取得反光球的3D座標，我們假設反光球的座標即代表手部各關節及指尖的座標。經由簡單的向量計算擷取5根手指共15個關節角度當特徵值，特徵值利用框架法做正規化及k-means演算法做分類。然後建立各動態手勢的隱藏馬可夫模型，最後辨識各動態手勢。
我們的辨識系統主要的優點在於(1)沒有繁雜的影像處理，(2)不需要發展複雜的演算法來擷取特徵值，(3)可以避免大部分的手勢遮蔽。我們自行定義了七種動態手勢，找了10位受試者，總共用140筆測試資料，實驗結果顯示整體辨識率是88.57%。

A dynamic hand gesture recognition system was developed in this study. There are four tasks in the study: (1) motion tracking and 3D coordinates obtaining, (2) feature extraction, (3) Hidden Markov Model (HMM) development, and (4) gesture recognition. A total of 21 markers were attached onto the joints and fingertips of the 10 participants. Vicon Motion Analysis Systems with 8 cameras was used to record the motion of 7 hand gestures and then the 3D coordinates of each marker were generated. Fifteen finger-joint-angle was calculated as the features of these gestures. The feature angles were then normalized in time and classify into group using k-means method and then were coded. Finally, Hidden Markov Models (HMM) were built and each hand gestures were used as input for gesture recognition.
The main merits of our system are (1) no multifarious image processing, (2) no need to develop complex algorithm for features extraction, and (3) being able to avoid most of the hand occlusion. As a result, the system is able to recognize 88.57% of the 140 hand gestures.

英文部分

1. Chen, F. S., Fu, C. M., and Huang, C. L. (2003). Hand gesture recognition using a real-time tracking method and hidden Markov models. Image and Vision Computing, Vol.21, pp.745-758.
2. Chua, C. S., Guan, H., and Ho, Y. K. (2002). Model based 3D hand posture estimation from a single 2D image. Image and Vision Computing, Vol.20, pp.191-202.
3. Davis, J. and Shah, M. (1994). Visual gesture recognition. Vision, Image and Signal Processing, 141(2), pp.101-106.
4. Derpanis, K. G. (2004). A Review of Vision-Based Hand Gestures. Department of Computer Science York University, internal report.
5. Erol, A., Bebis, G., Nicolescu, M., Boyle, R. D., and Twombly, X. (2005). A Review on Vision-Based Full DOF Hand Motion Estimation. IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, Vol.3, pp.75.
6. Fels, S. S. and Hinton, G. E. (1998). Glove-Talk II: A neural network interface which maps gestures to parallel format speech synthesizer controls. IEEE Transaction on Neural Networks, 9(1), pp.205–212.
7. Grobel, K. and Assan, M. (1997). Isolated sign language recognition using Hidden Markov Models systems. Proceeding of the IEEE International Conference on Computational Cybernetics and Simulation, Vol.1, pp.162-167.
8. Huang, C. L., Wu, M. S., and Jeng, S. H. (2000). Gesture recognition using the multi-PDM method and hidden Markov model. Image and Vision Computing, 18(11), pp.865-879.
9. Juang, B. H. and Rabiner, L. R. (1991). Hidden Markov Models for Speech Recognition. Technometrics, 33(3), pp.251-272.
10. Keskin, C., Erkan, A., and Akarun, L. (2003). Real time hand tracking and 3D gesture recognition for interactive interfaces using HMM. Proceeding of ICANN/ICONIP, pp.567-570.
11. Lee, C. S., Park, G., Kim, J. S., Bien, Z., Jang, W., and Kim, S. K. (1997). Real-time recognition system of Korean sign language based on elementary components. Proceedings of the Sixth IEEE International Conference on Fuzzy Systems, Vol.3, pp.1463-1468.
12. Lee, H. K. and Kim, J. H. (1998). Gesture spotting from continuous hand motion. Pattern Recognition Letters, 19(5-6), pp.513-520.
13. Liang, R. H. and Ouhyoung, M. (1998). A real-time continuous gesture recognition system for sign language. Proceeding of the IEEE International Conference on Automatic Face and Gesture Recognition, Vol.3, pp.558-567.
14. Ma, J., Gao, W., Wu, J., and Wang, C. (2000). A continuous Chinese sign language recognition system. Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition, pp.428-433.
15. MacDonald, I. L. and Zucchini, W. (1997). Hidden Markov and Other Models for Discrete-valued Time Series. Chapman & Hall, London.
16. Min, B. W., Yoon, H. S., Soh, J., Ohashi, T., and Ejima, T. (1999). Gesture-based editing system for graphic primitives and alphanumeric characters. Engineering Applications of Artificial Intelligence, 12(4), pp.429-441.
17. Ng, C. W. and Ranganath, S. (2002). Real-time gesture recognition system and application. Image and Vision Computing, 20(13-14), pp.993-1007.
18. Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), pp.257-286.
19. Ramamoorthy, A., Vaswani, N., Chaudhury, S., and Bannerjee, S. (2003). Recognition of dynamic hand gestures. Pattern Recognition, 36(9), pp.2069-2081.
20. Sato, Y., Kobayashi, Y., and Koike, H. (2000). Fast tracking of hands and fingertips in infrared images for augmented desk interface. IEEE Automatic Face and Gesture Recognition(FG2000), pp.462-467.
21. Sato, Y., Saito, M., and Koike, H. (2001). Real-Time Input of 3D Pose and Gestures of a User’s Hand and Its Applications for HCI. IEEE Virtual Reality, pp.79-86.
22. Starner, T., Auxier, J., Ashbrook, D., and Gandy, M. (2000). The Gesture Pendant: A Self-illuminating, Wearable, Infrared Computer Vision System for Home Automation Control and Medical Monitoring. Proceedings of IEEE International Symposium on Wearable Computing, pp.87-94.
23. Sturman, D. J. and Zeltzer, D. (1994). A survey of glove-based input. IEEE Computer Graphics and Appl., pp.30-39.
24. Ueda, E., Matsumoto, Y., Imai, M., and Ogasawara, T. (2003). A hand-pose estimation for vision-based human interfaces. IEEE Transactions on Industrial Electronics, 50(4), pp.676-684.
25. Utsumi, A. and Ohya, J. (1999). Multiple-Hand-Gesture Tracking using Multiple Cameras. Computer Vision and Pattern Recognition, pp.473-478.
26. Wilpon, J. G. and Rabiner, L. R. (1985). A modified k-means clustering algorithm for use in isolated word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(3), pp.587-594.
27. Wu, J., Gao, W., Song, Y., Liu, W., and Pang, B. (1998). A simple sign language recognition system based on data glove. Proceeding of the IEEE International Conference on Signal Processing Proceedings, Vol.2, pp.1257-1260.
28. Yoon, H. S., Soh, J., Bae, Y. J., and Yang, H. S. (2001). Hand gesture recognition using combined features of location, angle and velocity. Pattern Recognition, 34(7), pp.1491-1501.

中文部分

1. 王國榮，基於資料手套的智慧型手勢辨識之廣泛研究，碩士論文，國立台灣科技大學電機工程所，台北，民國90年。
2. 史傑州，應用感應手套模擬手部復健評估之研究，碩士論文，國立成功大學工業設計系，台南，民國89年。
3. 柯廷潔，利用虛擬實境技術進行個人電腦組裝訓練，碩士學位論文，國立交通大學資訊工程研究所，新竹，民國87年。
4. 范揚平，電腦簡報系統中以手勢替代滑鼠做操控功能，碩士學位論文，國立交通大學資訊工程研究所，新竹，民國86年。
5. 陳治宇，虛擬滑鼠：以視覺為基礎之手勢辨識，碩士學位論文，國立中山大學資訊工程研究所，高雄，民國92年。
6. 莊博文，潛藏馬可夫模型應用於轉換機率之估算正確性模擬研究，碩士學位論文，國立台中師範學院教育測驗與統計研究所，台中，民國91年。
7. 劉曜德，隱藏馬可夫模型觀測序列遺漏值處理之研究，碩士學位論文，國立台中師範學院教育測驗與統計研究所，台中，民國92年。
8. 程瑜銘，隱藏式馬可夫模型應用於水下聲源訊號識別之研究，碩士學位論文，中原大學資訊工程研究所，桃園，民國89年。
9. 謝郡青，以連續型隱藏式馬可夫模型來計算中文簽名之動態相似度值，碩士學位論文，元智大學電機與資訊工程研究所，桃園，民國86年。